© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5876
    Prev
    Next
    INDEX
    Explanations

    DuPont offers

    np_acts-logits-general · gemini-2.5-flash-lite

    sending texts for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{\
    0.44
     mathvariant
    0.41
    csname
    0.41
    cm
    0.39
     cm
    0.39
    ěl
    0.39
    楽
    0.38
    roman
    0.38
     Roman
    0.37
     }{\
    0.37
    POSITIVE LOGITS
     Januari
    0.48
     DECEMBER
    0.43
     Running
    0.43
     JANUARY
    0.42
     Coronado
    0.39
     পিপ
    0.39
     running
    0.39
    চো
    0.39
    Henderson
    0.38
    Situated
    0.38
    Activations Density 0.000%

    No Known Activations